JSON Files

// Primitive types (Int, String, etc) and Product types (case classes) encoders are
// supported by importing this when creating a Dataset.
import spark.implicits._

// A JSON dataset is pointed to by path.
// The path can be either a single text file or a directory storing text files
val path = "examples/src/main/resources/people.json"
val peopleDF = spark.read.json(path)

// The inferred schema can be visualized using the printSchema() method
peopleDF.printSchema()
// root
//  |-- age: long (nullable = true)
//  |-- name: string (nullable = true)

// Creates a temporary view using the DataFrame
peopleDF.createOrReplaceTempView("people")

// SQL statements can be run by using the sql methods provided by spark
val teenagerNamesDF = spark.sql("SELECT name FROM people WHERE age BETWEEN 13 AND 19")
teenagerNamesDF.show()
// +------+
// |  name|
// +------+
// |Justin|
// +------+

// Alternatively, a DataFrame can be created for a JSON dataset represented by
// a Dataset[String] storing one JSON object per string
val otherPeopleDataset = spark.createDataset(
  """{"name":"Yin","address":{"city":"Columbus","state":"Ohio"}}""" :: Nil)
val otherPeople = spark.read.json(otherPeopleDataset)
otherPeople.show()
// +---------------+----+
// |        address|name|
// +---------------+----+
// |[Columbus,Ohio]| Yin|
// +---------------+----+

import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;

// A JSON dataset is pointed to by path.
// The path can be either a single text file or a directory storing text files
Dataset<Row> people = spark.read().json("examples/src/main/resources/people.json");

// The inferred schema can be visualized using the printSchema() method
people.printSchema();
// root
//  |-- age: long (nullable = true)
//  |-- name: string (nullable = true)

// Creates a temporary view using the DataFrame
people.createOrReplaceTempView("people");

// SQL statements can be run by using the sql methods provided by spark
Dataset<Row> namesDF = spark.sql("SELECT name FROM people WHERE age BETWEEN 13 AND 19");
namesDF.show();
// +------+
// |  name|
// +------+
// |Justin|
// +------+

// Alternatively, a DataFrame can be created for a JSON dataset represented by
// a Dataset<String> storing one JSON object per string.
List<String> jsonData = Arrays.asList(
        "{\"name\":\"Yin\",\"address\":{\"city\":\"Columbus\",\"state\":\"Ohio\"}}");
Dataset<String> anotherPeopleDataset = spark.createDataset(jsonData, Encoders.STRING());
Dataset<Row> anotherPeople = spark.read().json(anotherPeopleDataset);
anotherPeople.show();
// +---------------+----+
// |        address|name|
// +---------------+----+
// |[Columbus,Ohio]| Yin|
// +---------------+----+

# spark is from the previous example.
sc = spark.sparkContext

# A JSON dataset is pointed to by path.
# The path can be either a single text file or a directory storing text files
path = "examples/src/main/resources/people.json"
peopleDF = spark.read.json(path)

# The inferred schema can be visualized using the printSchema() method
peopleDF.printSchema()
# root
#  |-- age: long (nullable = true)
#  |-- name: string (nullable = true)

# Creates a temporary view using the DataFrame
peopleDF.createOrReplaceTempView("people")

# SQL statements can be run by using the sql methods provided by spark
teenagerNamesDF = spark.sql("SELECT name FROM people WHERE age BETWEEN 13 AND 19")
teenagerNamesDF.show()
# +------+
# |  name|
# +------+
# |Justin|
# +------+

# Alternatively, a DataFrame can be created for a JSON dataset represented by
# an RDD[String] storing one JSON object per string
jsonStrings = ['{"name":"Yin","address":{"city":"Columbus","state":"Ohio"}}']
otherPeopleRDD = sc.parallelize(jsonStrings)
otherPeople = spark.read.json(otherPeopleRDD)
otherPeople.show()
# +---------------+----+
# |        address|name|
# +---------------+----+
# |[Columbus,Ohio]| Yin|
# +---------------+----+

# A JSON dataset is pointed to by path.
# The path can be either a single text file or a directory storing text files.
path <- "examples/src/main/resources/people.json"
# Create a DataFrame from the file(s) pointed to by path
people <- read.json(path)

# The inferred schema can be visualized using the printSchema() method.
printSchema(people)
## root
##  |-- age: long (nullable = true)
##  |-- name: string (nullable = true)

# Register this DataFrame as a table.
createOrReplaceTempView(people, "people")

# SQL statements can be run by using the sql methods.
teenagers <- sql("SELECT name FROM people WHERE age >= 13 AND age <= 19")
head(teenagers)
##     name
## 1 Justin